Machine Learning Driven Chemical Compound Replacement Technology

1. A computer-implemented method of suggesting chemical compounds as substitutes for a chemical compound that is present in a food item, comprising: training an artificial intelligence model based on first digital data representing plurality of source chemical compounds and second digital data representing flavors and odors of the plurality of source chemical compounds, the first digital data including a structural representation of each source chemical compound of the plurality of source chemical compounds; applying the trained artificial intelligence model to the plurality of source chemical compounds to generate a plurality of source compound embeddings for the plurality of source chemical compounds, each of the plurality of source chemical embeddings includes information relating to a chemical structure and flavor of a corresponding source chemical compound, the trained artificial intelligence model is based on structures and flavors of the plurality of source chemical compounds; wherein modeling of flavors of the plurality of source chemical compounds is based on the structures of the plurality of source chemical compounds; applying the trained artificial intelligence model to a target chemical compound to generate a target compound embedding for the target chemical compound, the target chemical compound is a chemical compound that is present in a particular food item, the target chemical embedding includes information relating to a chemical structure and flavor of the target chemical compound; and determining, for each source chemical compound of the plurality of source chemical compounds, a closeness value between the target compound embedding for the target chemical compound and the source compound embedding for a respective source chemical compound, and identifying a particular source chemical compound that has the greatest closeness value among all closeness values of the plurality of source chemical compounds as an alternative chemical compound.

2. The method of claim 1 , wherein training the artificial intelligence model comprises: transforming each of the plurality of source chemical compounds into a graph that includes nodes representing atoms of a respective source chemical compound and edges representing bonds between the atoms of the respective source chemical compound; applying a graph neural network on the graph; processing an output from layers of the graph neural network through dense layers of a feed forward network.

3. The method of claim 2 , wherein processing the output from the layers of the graph neural network comprises: generating a representation of the graph; matching the representation of the graph with the second digital data.

4. The method of claim 3 , wherein generating the representation of the graph comprises performing a computation on node representations of the nodes in the graph.

5. The method of claim 2 , wherein the plurality of source compound embeddings for the plurality of source chemical compounds and the target compound embedding for the target chemical compound are retrieved from the dense layers of the feed forward network.

6. The method of claim 1 , wherein the alternative chemical compound is determined using a distance metric.

7. The method of claim 1 , further comprising: performing gas chromatography mass spectrometry (GCMS) analysis on the particular food item; generating, from the GCMS analysis, a list of chemical compounds, wherein each of the chemical compounds in the list of chemical compounds is a chemical compound present in the particular food item; wherein the target chemical compound is identified from the list of chemical compounds.

8. The method of claim 1 , further comprising determining one or more plant-based ingredients containing the alternative chemical compounds.

9. One or more non-transitory computer-readable storage media storing one or more instructions programmed for suggesting chemical compounds as substitutes for a chemical compound that is present in a product, when executed by one or more computing devices, cause: training an artificial intelligence model based on first digital data representing plurality of source chemical compounds and second digital data representing functional properties of the plurality of source chemical compounds, the first digital data including a structural representation of each source chemical compound of the plurality of source chemical compounds; applying the trained artificial intelligence model to the plurality of source chemical compounds to generate a plurality of source compound embeddings for the plurality of source chemical compounds, each of the plurality of source chemical embeddings includes information relating to a chemical structure and flavor of a corresponding source chemical compound, the trained artificial intelligence model is based on structures and flavors of the plurality of source chemical compounds; wherein modeling of flavors of the plurality of source chemical compounds is based on the structures of the plurality of source chemical compounds; applying the trained artificial intelligence model to a target chemical compound to generate a target compound embedding for the target chemical compound, the target chemical compound is a chemical compound that is present in a particular product, the target chemical embedding includes information relating to a chemical structure and flavor of the target chemical compound; and determining, for each source chemical compound of the plurality of source chemical compounds, a closeness value between the target compound embedding for the target chemical compound and the source compound embedding for a respective source chemical compound, and identifying a particular source chemical compound that has the greatest closeness value among all closeness values of the plurality of source chemical compounds as an alternative chemical compound.

10. The one or more non-transitory computer-readable storage media of claim 9 , wherein training the artificial intelligence model comprises: transforming each of the plurality of source chemical compounds into a graph that includes nodes representing atoms of a respective source chemical compound and edges representing bonds between the atoms of the respective source chemical compound; applying a graph neural network on the graph; processing an output from layers of the graph neural network through dense layers of a feed forward network.

11. The one or more non-transitory computer-readable storage media of claim 10 , wherein processing the output from the layers of the graph neural network comprises: generating a representation of the graph; matching the representation of the graph with the second digital data.

12. The one or more non-transitory computer-readable storage media of claim 11 , wherein generating the representation of the graph comprises performing a computation on node representations of the nodes in the graph.

13. The one or more non-transitory computer-readable storage media of claim 10 , wherein the plurality of source compound embeddings for the plurality of source chemical compounds and the target compound embedding for the target chemical compound are retrieved from the dense layers of the feed forward network.

14. The one or more non-transitory computer-readable storage media of claim 9 , wherein the alternative chemical compound is determined using a distance metric.

15. The one or more non-transitory computer-readable storage media of claim 9 , wherein the one or more instructions, when executed by the one or more computing devices, further cause: performing gas chromatography mass spectrometry (GCMS) analysis on the particular product; generating, from the GCMS analysis, a list of chemical compounds, wherein each of the chemical compounds in the list of chemical compounds is a chemical compound present in the particular product; wherein the target chemical compound is identified from the list of chemical compounds.

16. A computing system comprising: one or more computer systems comprising one or more hardware processors and storage media; and instructions stored in the storage media and which, when executed by the computing system, cause the computing system to perform: training an artificial intelligence model based on first digital data representing plurality of source chemical compounds and second digital data representing functional properties of the plurality of source chemical compounds, the first digital data including a structural representation of each source chemical compound of the plurality of source chemical compounds; applying the trained artificial intelligence model to the plurality of source chemical compounds to generate a plurality of source compound embeddings for the plurality of source chemical compounds, each of the plurality of source chemical embeddings includes information relating to a chemical structure and flavor of a corresponding source chemical compound, the trained artificial intelligence model is based on structures and flavors of the plurality of source chemical compounds; wherein modeling of flavors of the plurality of source chemical compounds is based on the structures of the plurality of source chemical compounds; applying the trained artificial intelligence model to a target chemical compound to generate a target compound embedding for the target chemical compound, the target chemical compound is a chemical compound that is present in a particular product, the target chemical embedding includes information relating to a chemical structure and flavor of the target chemical compound; and determining, for each source chemical compound of the plurality of source chemical compounds, a closeness value between the target compound embedding for the target chemical compound and the source compound embedding for a respective source chemical compound, and identifying a particular source chemical compound that has the greatest closeness value among all closeness values of the plurality of source chemical compounds as an alternative chemical compound.

17. The computing system of claim 16 , wherein training the artificial intelligence model comprises: transforming each of the plurality of source chemical compounds into a graph that includes nodes representing atoms of a respective source chemical compound and edges representing bonds between the atoms of the respective source chemical compound; applying a graph neural network on the graph; processing an output from layers of the graph neural network through dense layers of a feed forward network.

18. The computing system of claim 17 , wherein processing the output from the layers of the graph neural network comprises: generating a representation of the graph; matching the representation of the graph with the second digital data.

19. The computing system of claim 18 , wherein generating the representation of the graph comprises performing a computation on node representations of the nodes in the graph.

20. The computing system of claim 17 , wherein the plurality of source compound embeddings for the plurality of source chemical compounds and the target compound embedding for the target chemical compound are retrieved from the dense layers of the feed forward network.